In-depth performance analysis of an EEG based neonatal seizure detection algorithm.

ABSTRACT:

Objective

To describe a novel neurophysiology based performance analysis of automated seizure detection algorithms for neonatal EEG to characterize features of detected and non-detected seizures and causes of false detections to identify areas for algorithmic improvement.

Methods

EEGs of 20 term neonates were recorded (10 seizure, 10 non-seizure). Seizures were annotated by an expert and characterized using a novel set of 10 criteria. ANSeR seizure detection algorithm (SDA) seizure annotations were compared to the expert to derive detected and non-detected seizures at three SDA sensitivity thresholds. Differences in seizure characteristics between groups were compared using univariate and multivariate analysis. False detections were characterized.

Results

The expert d

SUBMITTER: Mathieson S 

PROVIDER: S-EPMC4840013 | biostudies-literature | 2016 May

REPOSITORIES: biostudies-literature